bitwarden-shepherd

bitwarden-shepherd is a plugin for Claude Code from bitwarden/ai-plugins. Its manifest loads nothing; the 7 skills it bundles cost 257 tokens per session together, scanned A, original, no licence file.

A technical-strategy agent for Bitwarden that guides ideas through architecture review and a five-phase software initiative process, from identification through implementation.

In plain words
What is it for?
Use it to guide Bitwarden strategy ideas through evaluation, research, proof of concept, scoping, commitment, and implementation.
Why use it?
It provides a defined path for turning a technical idea into an implemented initiative. The description does not specify the agent's individual commands or outputs.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it to guide Bitwarden strategy ideas through evaluation, research, proof of…

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add bitwarden/ai-plugins/plugin install bitwarden-shepherd
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/bitwarden/ai-plugins

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for bitwarden-shepherd

README.md
[![agentmods](https://agentmods.dev/badge/plugins/bitwarden/ai-plugins/bitwarden-shepherd.svg)](https://agentmods.dev/plugins/bitwarden/ai-plugins/bitwarden-shepherd)
Your own site
<a href="https://agentmods.dev/plugins/bitwarden/ai-plugins/bitwarden-shepherd"><img src="https://agentmods.dev/badge/plugins/bitwarden/ai-plugins/bitwarden-shepherd.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 7 skills cost 257 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

bitwarden-shepherd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/bitwarden-shepherd/.claude-plugin/plugin.json · 24 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 24 lines scan A 1232a5e8eeaf

Subscribe to this mod's changes

bitwarden-shepherd is a plugin published in the GitHub repository bitwarden/ai-plugins (145 stars, last pushed yesterday), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.